Training in progress, step 1400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:020b8287f73b421e6b874533d8b2ed11de5c0eff953cef60c3f34994887f821b
+oid sha256:bda8507d5c5066f31513bff07c4d9f0892568afb4024128f972ec1b6da9b2ac2
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8856891d17903f6322204042a50f1915a9479d735ba8dd1040155c0c61bdb245
+oid sha256:7e53295bee557fed0dcdde3db2f871a7b3f220fc88e63c4cb7d6788ecdf83f57
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a1d0fa3c6d845cfcdb586fc5456e69f414fd350362eb5b418907a512e6ec4c
+oid sha256:3e4490c26af2695a2b327922ff3f2cc285daad2f6354ff581e32798a9b8e42b8
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
+oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.331716775894165,
-  "best_model_checkpoint": "./outputs/checkpoint-1300",
-  "epoch": 0.9471766848816029,
+  "best_metric": 2.3074026107788086,
+  "best_model_checkpoint": "./outputs/checkpoint-1400",
+  "epoch": 1.0200364298724955,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,13 +189,27 @@
       "eval_samples_per_second": 30.663,
       "eval_steps_per_second": 3.837,
       "step": 1300
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0002,
+      "loss": 2.3005,
+      "step": 1400
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 2.3074026107788086,
+      "eval_runtime": 204.9029,
+      "eval_samples_per_second": 30.619,
+      "eval_steps_per_second": 3.831,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.792256256581632e+16,
+  "total_flos": 4.091805541361664e+16,
   "trial_name": null,
   "trial_params": null
 }